Xiuyi Lou

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Reasoning & Chain-of-Thought (1)RLHF & Preference Learning (1)

Frequent co-authors

Zicheng Xu (1)Yu-Neng Chuang (1)Hoang Anh Duy Le (1)Zhaozhuo Xu (1)

Papers (1)

Jul 8, 2026

Xiuyi Lou +65d ago

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

TACO effectively mitigates the reinforcement of erroneous reasoning in LLMs by distinguishing between useful and unreliable tokens, leading to improved training stability and performance.

Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang +4

Reasoning & Chain-of-Thought RLHF & Preference Learning

Search

Xiuyi Lou

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)